Mehdi Jafarnia-Jahromi

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 19

Top Topics

Markov Decision Processes

Top Venues

Publications

Mehdi Jafarnia-Jahromi, Rahul A. Jain, Ashutosh Nayyar
A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent. AISTATS (2024)
Mehdi Jafarnia-Jahromi, Liyu Chen, Rahul Jain, Haipeng Luo
Posterior sampling-based online learning for the stochastic shortest path model. UAI (2023)
Mehdi Jafarnia-Jahromi, Rahul Jain, Ashutosh Nayyar
Online Learning for Unknown Partially Observable MDPs. AISTATS (2022)
William Chang, Mehdi Jafarnia-Jahromi, Rahul Jain
Online Learning for Cooperative Multi-Player Multi-Armed Bandits. CDC (2022)
Mehdi Jafarnia-Jahromi, Rahul Jain, Ashutosh Nayyar
Online Learning for Unknown Partially Observable MDPs. CoRR (2021)
Mehdi Jafarnia-Jahromi, Liyu Chen, Rahul Jain, Haipeng Luo
Online Learning for Stochastic Shortest Path Model via Posterior Sampling. CoRR (2021)
Liyu Chen, Mehdi Jafarnia-Jahromi, Rahul Jain, Haipeng Luo
Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path. NeurIPS (2021)
William Chang, Mehdi Jafarnia-Jahromi, Rahul Jain
Online Learning for Cooperative Multi-Player Multi-Armed Bandits. CoRR (2021)
Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo, Rahul Jain
Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation. AISTATS (2021)
Mehdi Jafarnia-Jahromi, Rahul Jain, Ashutosh Nayyar
Learning Zero-sum Stochastic Games with Posterior Sampling. CoRR (2021)
Liyu Chen, Mehdi Jafarnia-Jahromi, Rahul Jain, Haipeng Luo
Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path. CoRR (2021)
Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo, Rahul Jain
Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation. CoRR (2020)
Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo, Hiteshi Sharma, Rahul Jain
Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes. ICML (2020)
Mehdi Jafarnia-Jahromi, Chen-Yu Wei, Rahul Jain, Haipeng Luo
A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret. CoRR (2020)
Mehdi Jafarnia-Jahromi, Rahul Jain
Non-indexability of the stochastic appointment scheduling problem. Autom. 118 (2020)
Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo, Hiteshi Sharma, Rahul Jain
Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes. CoRR (2019)
Hiteshi Sharma, Mehdi Jafarnia-Jahromi, Rahul Jain
Approximate Relative Value Learning for Average-reward Continuous State MDPs. UAI (2019)
Mehdi Jafarnia-Jahromi, Tasmin Chowdhury, Hsin-Tai Wu, Sayandev Mukherjee
PPD: Permutation Phase Defense Against Adversarial Examples in Deep Learning. ICMLA (2019)
Mehdi Jafarnia-Jahromi, Tasmin Chowdhury, Hsin-Tai Wu, Sayandev Mukherjee
PPD: Permutation Phase Defense Against Adversarial Examples in Deep Learning. CoRR (2018)